CN109582829B

CN109582829B - Processing method, device, equipment and readable storage medium

Info

Publication number: CN109582829B
Application number: CN201811467268.0A
Authority: CN
Inventors: 于博杰; 孟广博
Original assignee: Lenovo Beijing Ltd
Current assignee: Lenovo Beijing Ltd
Priority date: 2018-12-03
Filing date: 2018-12-03
Publication date: 2021-05-18
Anticipated expiration: 2038-12-03
Also published as: CN109582829A

Abstract

The application discloses a processing method, a processing device and a readable storage medium, wherein a node association graph and a first parameter are obtained, if the first parameter represents that the node association graph comprises nodes corresponding to different users respectively, a key node is found from the node association graph, the key node is connected with the first node and at least one second node, the probability that the key node and the at least one second node belong to different users in the nodes contained in the node association graph is the maximum, and edges between the key node and the at least one second node are cut off, so that at least one sub-association graph is obtained; therefore, one sub-association diagram only comprises nodes corresponding to one user respectively, or the number of different users corresponding to one sub-association diagram is smaller than that of different users corresponding to the currently obtained node association diagram compared with the prior art, so that the obtained user image is more accurate than that in the prior art.

Description

Processing method, device, equipment and readable storage medium

Technical Field

The present application relates to the field of databases, and more particularly, to a processing method, apparatus, device, and readable storage medium.

Background

User portrayal, also called user roles, is an effective tool for delineating target users and connecting user appeal and design directions, and is widely applied in various fields, for example, user portrayal is used for recommending interesting advertisements for users. The user representation includes at least a node association graph.

The node association graph is described below, for example, a user has multiple different nodes, such as mobile phone numbers, mailboxes, cookies, and so on. In the process of obtaining the node association graph, the user multi-channel information needs to be communicated, namely, the association relations between different nodes of the same user are obtained, and the nodes with the association relations are connected, so that the node association graph is formed, for example, a user logs in a website by using a mailbox at a client and browses contents on the website, a server sends a cookie to the client, the mailbox has the association relation with the cookie, and the mailbox and the cookie can be connected by using an edge; for another example, the user inputs equipment maintenance information in an enterprise service page displayed by the client, the equipment maintenance information includes a mobile phone number and an email of the user, and the enterprise server randomly allocates an enterprise service ID to the user, so that the enterprise service ID, the mobile phone number and the email have an association relationship, and the three nodes can be connected with each other by using edges.

However, the currently obtained node association graph includes nodes corresponding to different users, which results in inaccurate user representation.

Disclosure of Invention

In view of this, the present application provides a processing method, an apparatus, a device and a readable storage medium, and the following technical solutions are provided in the present application:

a method of processing, comprising:

acquiring a node association graph, wherein the node association graph comprises at least two nodes and edges connecting every two nodes, one edge represents that the two nodes connected by the edge have an association relationship, the association relationship represents that the two nodes connected by the edge can be acquired at least in the process of executing the same event, and the node association graph is taken as a to-be-processed association graph;

acquiring a first parameter, wherein the first parameter represents whether the association diagram to be processed contains nodes respectively corresponding to different users;

if the first parameter represents that the association graph to be processed comprises nodes respectively corresponding to different users, acquiring a key node from the nodes contained in the association graph to be processed;

the key node is connected with the first node and at least one second node, and the probability that the key node and the at least one second node belong to different users is the maximum in the nodes contained in the association graph to be processed;

at least disconnecting the edges between the key nodes and the at least one second node respectively to obtain at least one target sub-association graph; one target sub-association graph corresponds to one user.

Preferably, the disconnecting at least the edge between the key node and the at least one second node, respectively, to obtain at least one target sub-association graph includes:

disconnecting the edges between the key nodes and the at least one second node respectively to obtain at least one sub-association graph;

and for each sub-association graph, taking the sub-association graph as a to-be-processed association graph, and returning to the step of obtaining the first parameter until the first parameter represents that the to-be-processed association graph only contains nodes respectively corresponding to the same user, so as to obtain at least one target sub-association graph.

Preferably, the edges included in the association graph to be processed are directed edges, and the direction of one directed edge is that a node with a high priority points to a node with a low priority;

acquiring key nodes from the nodes contained in the correlation graph to be processed comprises the following steps:

acquiring at least one candidate edge node from the nodes contained in the correlation diagram to be processed, wherein the degree of entry of the candidate edge node is 0 and the degree of exit is greater than 1 or the degree of exit is 0 and the degree of entry is greater than 1;

and acquiring the key node from the at least one candidate edge node.

Preferably, the to-be-processed association graph further includes a weight corresponding to each directed edge, and the weight corresponding to one directed edge represents the number of different events of two nodes connected to the directed edge obtained in the process of executing different events;

obtaining the key node from the at least one candidate node comprises:

for each candidate edge node, acquiring maximum weight from the weights respectively corresponding to the directed edges connecting the candidate edge node to obtain the maximum weight respectively corresponding to the at least one candidate edge node;

obtaining a candidate edge node corresponding to a minimum weight from maximum weights respectively corresponding to the at least one candidate edge node, wherein the candidate edge node corresponding to the minimum weight is the key node;

and the weight of the directed edge connecting the key node and the first node is the maximum.

Preferably, the dependency graph to be processed contains at least one type of node, and the obtaining the first parameter includes any one of the following:

if the total number of the nodes contained in the correlation diagram to be processed is greater than or equal to a first preset value, acquiring a first parameter representing that the correlation diagram to be processed contains the nodes respectively corresponding to different users; if the number of the nodes contained in the association graph to be processed is smaller than the first preset value, acquiring a first parameter representing that the association graph to be processed does not contain the nodes respectively corresponding to different users;

or the like, or, alternatively,

if the number of the nodes belonging to any type and contained in the correlation diagram to be processed is larger than or equal to a corresponding second preset value, acquiring a first parameter representing that the correlation diagram to be processed contains nodes respectively corresponding to different users; if the number of the nodes belonging to each type contained in the correlation diagram to be processed is respectively smaller than the corresponding second preset value, acquiring a first parameter representing that the correlation diagram to be processed does not contain the nodes respectively corresponding to different users;

or the like, or, alternatively,

if the total number of nodes contained in the correlation diagram to be processed is greater than or equal to a first preset value, and the number of nodes belonging to any type contained in the correlation diagram to be processed is greater than or equal to a corresponding second preset value, acquiring a first parameter representing that the correlation diagram to be processed contains nodes respectively corresponding to different users; and if the number of the nodes contained in the association graph to be processed is less than the first preset value, and the number of the nodes belonging to each type contained in the association graph to be processed is less than the corresponding second preset value, acquiring a first parameter representing that the association graph to be processed does not contain the nodes respectively corresponding to different users.

Preferably, the edges included in the node association graph are directed edges, and the direction of one directed edge is that a node with a high priority points to a node with a low priority; the obtaining of the node association graph comprises:

acquiring the at least two nodes;

for each pair of two nodes with incidence relation, determining node types to which the two nodes respectively belong;

determining priority levels respectively corresponding to the two nodes based on the priority levels respectively corresponding to the preset node types;

and determining the direction of the directed edge connecting the two nodes based on the priority levels respectively corresponding to the two nodes so as to obtain the directed edges respectively corresponding to the two nodes with the association relationship.

A processing apparatus, comprising:

the first acquisition module is used for acquiring a node association graph, wherein the node association graph comprises at least two nodes and edges connecting every two nodes, one edge represents that the two nodes connected by the edge have an association relationship, the association relationship represents that the two nodes connected by the edge can be acquired at least in the process of executing the same event, and the node association graph is used as an association graph to be processed;

the second obtaining module is used for obtaining a first parameter, and the first parameter represents whether the association diagram to be processed contains nodes corresponding to different users respectively;

a third obtaining module, configured to obtain a key node from nodes included in the to-be-processed association graph if the first parameter indicates that the to-be-processed association graph includes nodes corresponding to different users, respectively;

the fourth obtaining module is configured to at least disconnect edges between the key nodes and the at least one second node, respectively, to obtain at least one target sub-association graph; one target sub-association graph corresponds to one user.

Preferably, the edges included in the association graph to be processed are directed edges, and the direction of one directed edge is that a node with a high priority points to a node with a low priority; the third obtaining module includes:

a first obtaining unit, configured to obtain at least one candidate edge node from nodes included in the to-be-processed association graph, where an entry degree of the candidate edge node is 0 and an exit degree is greater than 1, or the exit degree is 0 and the entry degree is greater than 1;

a second obtaining unit, configured to obtain the key node from the at least one candidate edge node.

An electronic device, comprising:

a memory for storing a program;

a processor configured to execute the program, the program specifically configured to:

A readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the steps comprised in any of the processing methods described above.

According to the technical scheme, compared with the prior art, the node association graph and the first parameter are obtained, if the first parameter represents that the node association graph comprises nodes corresponding to different users respectively, a key node is found from the node association graph, the key node is connected with the first node and at least one second node, the probability that the key node and the at least one second node belong to different users in the nodes contained in the node association graph is the maximum, and edges between the key node and the at least one second node are cut off, so that at least one sub-association graph is obtained; for example, the node association graph obtained in the prior art may include at least nodes corresponding to three users, and in the present application, a sub-association graph may include only nodes corresponding to one or two users, so that the obtained user representation is more accurate than that in the prior art.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.

FIG. 1 is a flow chart of a processing method disclosed in an embodiment of the present application;

FIG. 2 illustrates a node association graph;

FIG. 3 illustrates a key node diagram contained in a dependency graph to be processed;

FIG. 4 illustrates a process diagram for obtaining at least one target sub-association graph;

FIG. 5 illustrates a node dependency graph diagram including directed edges;

FIG. 6 is a schematic diagram illustrating the determination of candidate edge nodes in a dependency graph to be processed;

7a-7b illustrate a process diagram for determining key nodes in candidate edge nodes;

8a-8b illustrate a process diagram for breaking an edge between a switch key node and a second node;

FIG. 9 illustrates a schematic diagram of determining a target sub-association map;

FIG. 10 is a schematic structural diagram of a processing apparatus according to an embodiment of the disclosure;

fig. 11 is a block diagram of a hardware structure of a processing device according to an embodiment of the present disclosure.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The processing method provided by the embodiment of the application can be suitable for various scenes needing to obtain user portraits, such as advertisements or videos which are interesting to the user, and the like, wherein the user portraits at least comprise node association graphs. The method includes the steps that in the process of obtaining a node association diagram, a user multi-channel information needs to be communicated to obtain a plurality of nodes with association relations, the nodes with the association relations in the application refer to the nodes which can be obtained at least in the process of executing the same event, for example, if electronic equipment of a user needs to be maintained, and when repair processing is carried out on a website, a mobile phone number and a mailbox of the user need to be filled in an interface displayed by the website; when a user performs initial maintenance, a background server of a website may assign an enterprise service ID, and for the repair event, a node having an association relationship includes: mobile phone number, mailbox, enterprise service ID. For another example, if the user needs the mailbox of the user to assist in verifying the identity of the user during logging in the chat account, for the login event, the nodes having the association relationship include: chat accounts and mailboxes. For another example, in a shopping website, a user may input his/her mobile phone number, and in a shopping event, the nodes having an association relationship include: a mobile phone number, a shopping account number.

If the mailbox in the repair reporting event is the same as the mailbox in the login event, and the mobile phone number in the shopping event is the same as the mobile phone number in the repair reporting event, the mobile phone number, the mailbox, the enterprise service ID, the chat account number and the shopping account number belong to the same node association graph.

It will be appreciated that different users may enter the same information, for example, in a repair incident, a user may consider the mailbox to be unimportant and may fill out a mailbox at random; the mailboxes randomly filled by different users may be the same; this results in the obtained node association graph including nodes corresponding to different users respectively.

According to the method and the device, the obtained node association graph can be processed, the node association graph is divided into a plurality of sub-association graphs, the number of different users corresponding to one sub-association graph is smaller than that of different users corresponding to the node association graph, and therefore the obtained user portrait is more accurate. For example, the mobile phone number reserved by the user 1 in a certain shopping website is phone1, the mailbox is Email1, the mobile phone number reserved by the user 2 in the shopping website is phone2, and the mailbox is Email1, it is obvious that the mailboxes reserved by the user 1 and the user 2 in the shopping website are the same, and therefore the obtained node association graph includes phone1, phone2, and Email1, that is, the node association graph includes nodes corresponding to the user 1 and the user 2, respectively, at this time, the application can split the obtained node association graph into two sub-association graphs, which are respectively defined as sub-association graph 1 and sub-association graph 2, where the sub-association graph 1 includes only the node corresponding to the user 1, and the sub-association graph 2 includes only the node corresponding to the user 2, and therefore, the obtained user images of the user 1 and the user 2 are more accurate.

In the embodiment of the present application, "sub association graph" is referred to as "sub association graph" because "sub association graph" is obtained by splitting from "node association graph"; in essence, the sub-association graphs are also node association graphs.

Referring to fig. 1, a flow chart of a processing method disclosed in the embodiment of the present application is shown, where the method includes:

step S100, a node association graph is obtained, the node association graph comprises at least two nodes and edges connecting every two nodes, and the node association graph is used as a to-be-processed association graph.

The two nodes connected by the edge are represented by one edge and have an incidence relation, and the incidence relation represents that the two nodes connected by the edge can be acquired at least in the process of executing the same event.

Optionally, in this embodiment of the present application, a node may be an identifier associated with a user identity, for example, one node may be any one of a mobile phone number, a mailbox, a cookie, an enterprise service ID, an S/N, a MAC, an IMEI, a customer ID, and an account.

The above-mentioned identification is explained below,

the cookie refers to data stored on a local terminal of the user in order to identify the user identity and perform session tracking after the user browses a website; the enterprise service ID may be an ID automatically allocated by a background server of the website, for example, the enterprise service ID in the repair event, such as a lenoov ID; S/N (Serial Number) is the unique identification of the notebook computer by the manufacturer; the MAC (Media Access Control Address) is an Address used to confirm the location of a device on the network; the IMEI (International Mobile Equipment Identity) is the unique Identity of the Mobile communication device. CustomerID refers to the ID assigned to the call repair when the user calls the electronic device to perform repair processing on the electronic device. In the event of a call repair, the nodes with the association relationship include: a telephone number, and a CustomerID.

The account number may be any one of a chat account number, a shopping account number, and a payment account number.

In the embodiment of the present application, different types of nodes may be divided, and optionally, the node types include: at least one of a mobile phone number type, a mailbox type, a cookie type, an enterprise service ID type, an S/N type, a MAC type, an IMEI type, a CustomerID type, and an account number type.

Optionally, a user may have at least one type of node, for example, a user has a node belonging to at least one type of a mobile phone number type, a mailbox type, a cookie type, an enterprise service ID type, an S/N type, an MAC type, an IMEI type, a customer ID type, and an account number type; optionally, for a type of node, a user may have multiple nodes, for example, a user has 3 nodes belonging to a mobile phone number type, that is, 3 mobile phone numbers.

Multiple different nodes that a user has, or multiple different nodes that different users have, may have an associative relationship. Connecting the nodes with the association relationship can obtain a node association graph, wherein the node association graph may include two or more nodes, and edges connecting the nodes are arranged between every two nodes.

Referring to fig. 2, a schematic diagram of a node association graph is illustrated. In the figure, A, B, C and D are 4 nodes included in the node association graph, where node a has an association relationship with node B, C, D, for example, the nodes having an association relationship in the website repair event include a and B, the nodes having an association relationship in the shopping event include a and C, and the nodes having an association relationship in the telephone repair event include a and D; the nodes a in the node association graph are each connected to the node B, C, D by an edge. Since any two nodes in B, C, D do not occur in the same event, there is no edge between any two nodes in B, C, D.

Optionally, in this embodiment of the application, the nodes with the same shape may belong to the same node type; nodes with different shapes belong to different node types, taking fig. 2 as an example, the nodes B, C, D with the same shape belong to the same node type; optionally, in this embodiment of the present application, the nodes with the same shape may belong to different node types. Nodes of different shapes may belong to the same node type.

It has been explained in the foregoing that there is an association relationship between two nodes connected by each edge in the node association graph. In general, a plurality of nodes of the same user have an association relationship, so that two nodes connected by each edge in the node association graph have a certain probability of belonging to the same user. In addition, the above-mentioned association relationship indicates that at least two nodes connected by an edge can be obtained in the process of executing the same event, that is, two nodes connected by an edge are obtained in the process of executing the same event, where the completion of one or more operations performed by a user in one or more interfaces indicates that an event is generated. For example, if the user 1 finishes shopping in a certain shopping website, that is, a shopping event is generated, and if the shopping website obtains a mobile phone number and a mailbox in the process of executing the shopping event by the user 1, two nodes of the mobile phone number and the mailbox can be generated in the shopping event, the two nodes can be connected through one edge in the step, so that when the event is executed, the two nodes of the mobile phone number and the mailbox connected through one edge can be simultaneously obtained.

It can be understood that, if the same user executes an event, the electronic device will acquire the corresponding node only when the event is executed for the first time; for example, when the electronic device is first reported on the website, a mobile phone number and an email box may need to be input, and the background server of the website automatically allocates the enterprise service ID, but when the electronic device or other electronic devices are reported again, the mobile phone number and the email box do not need to be input again, and the background server of the website does not allocate the enterprise service ID again; the initial mobile phone number, the mailbox and the enterprise service ID are used; optionally, in the application scenario where the node needs to be acquired only by performing the first time, no matter how many repair reports of the electronic device are performed in the application scenario, it is an event for the embodiment of the present application, or only the first time performed event is regarded as an event.

It can be understood that, if the same user executes the same thing many times, the electronic device needs to repeatedly obtain the corresponding node; for example, when the electronic device is first reported on a website, a mobile phone number and an email box may need to be input, a background server of the website automatically allocates an enterprise service ID, when the electronic device or other electronic devices are reported again, the mobile phone number and the email box still need to be input again, and the background server of the website also allocates the enterprise service ID again; the initial mobile phone number, the mailbox and the enterprise service ID are not used, and optionally, one event corresponds to one event in the application scene that the node needs to be repeatedly acquired in the process of executing the same event for multiple times; optionally, in the application scenario that the node needs to be repeatedly acquired in the process of executing the same event for multiple times, no matter how many times the repair of the electronic device is executed in the application scenario, it is an event for the embodiment of the present application, or only the event that is executed for the first time is regarded as an event.

Step S110, obtaining a first parameter, wherein the first parameter represents whether the correlation diagram to be processed contains nodes respectively corresponding to different users.

Optionally, the association graph to be processed may include nodes corresponding to different users, and in this step, a first parameter may be obtained, where the first parameter may be used to indicate whether the association graph to be processed includes nodes corresponding to different users. Optionally, the first parameter may be 0 or 1, where when the first parameter is 0, it indicates that the to-be-processed association graph does not include nodes respectively corresponding to different users, and when the first parameter is 1, it indicates that the to-be-processed association graph includes nodes respectively corresponding to different users.

Step S120, if the correlation diagram to be processed comprises nodes respectively corresponding to different users, the first parameter represents that key nodes are obtained from the nodes contained in the correlation diagram to be processed.

The key node is connected with the first node and at least one second node, and the probability that the key node and the at least one second node belong to different users is the largest in the nodes contained in the association graph to be processed.

Optionally, the association graph to be processed may include at least three nodes, where one node is connected to another node, for example, a same user has two mobile phone numbers, and both the two mobile phone numbers have an association relationship with a mailbox of the user, so that there is a case where one node is connected to another plurality of nodes through edges in the association graph to be processed. For another example, the mobile phone number phone1 of the user 1 has an association relationship with the mailbox Email1, the mobile phone number phone2 of the user 2 also has an association relationship with the mailbox Email1, and a situation that one node is connected with a plurality of other nodes through an edge also exists in the to-be-processed association graph including the phone1, the phone2 and the Email 1.

When the obtained first parameter indicates that the association graph to be processed includes nodes respectively corresponding to different users, the step may obtain a key node in the association graph to be processed including the node. Optionally, the key node is a node to which other nodes are connected, and the probability that the other nodes include nodes belonging to different users is the highest. That is, the nodes connected to the key node may include nodes belonging to the same user as the key node and/or include nodes belonging to different users from the key node. Here, among the nodes connected to the key node, a node having a higher probability of belonging to the same user as the key node is defined as a first node, and among the nodes connected to the key node, a node having a higher probability of belonging to a different user from the key node is defined as a second node. It is understood that there may be one or more second nodes, and the probability that the key node and the second node belong to different users is the greatest.

Referring to fig. 3, a schematic diagram of key nodes included in the dependency graph to be processed is illustrated. Fig. 3 is a correlation diagram to be processed, which includes nodes corresponding to user 1 and user 2. In this step, a key node a may be obtained, where a node D connected to a is assumed to be a first node, and nodes B and C connected to a are assumed to be second nodes, where the probability that node a and node B, C belong to different users is the largest.

Step S130, at least disconnecting the edges between the key nodes and the at least one second node to obtain at least one target sub-association graph.

Wherein, one target sub-association graph corresponds to one user.

Specifically, since the probability that the key node and the second node belong to different users is the largest, the step may disconnect the edge between the key node and the second node to obtain at least one target sub-association graph, so that the number of different users corresponding to one target sub-association graph is smaller than the number of different users corresponding to the association graph to be processed.

Optionally, one target sub-association graph corresponds to only one user, that is, in this step, nodes belonging to different users in the association graph to be processed can be respectively split into different target sub-association graphs, so that the purpose of optimizing the user portrait is achieved.

Referring to fig. 4, a schematic diagram illustrating a process of obtaining at least one target sub-association graph is shown. The left graph of fig. 4 is a pending association graph, in which node a is a key node, node B, C is a second node, and node D is a first node. This step can break the edges between a and B and a and C to obtain the three target sub-correlation diagrams shown in the right diagram of fig. 4.

The application discloses a processing method, a node association graph and a first parameter are obtained, if the first parameter represents that the node association graph comprises nodes corresponding to different users respectively, a key node is found from the node association graph, the key node is connected with the first node and at least one second node, the probability that the key node and the at least one second node belong to different users in the nodes contained in the node association graph is the maximum, edges between the key node and the at least one second node are cut off, and therefore at least one sub-association graph is obtained; for example, the node association graph obtained in the prior art may include at least nodes corresponding to three users, and in the present application, a sub-association graph may include only nodes corresponding to one or two users, so that the obtained user representation is more accurate than that in the prior art.

Further, the nodes included in the node association graph obtained in step S100 may have priorities, the edges included in the node association graph may be directed edges, and the direction of one directed edge is that a node with a high priority points to a node with a low priority. Optionally, the priority level of the node may be obtained based on the probability of the node type to which the node belongs appearing in different users; the higher the probability of the node type appearing in different users is, the higher the priority level of the node is; for example, if all nodes are obtained from an electronic device repair reporting website, since a background server of the website allocates an enterprise service ID in the process of applying for repair reporting on the electronic device in the website, the probability that a node of the enterprise service ID type appears in different users is the greatest, and the priority level of the enterprise service ID is the highest.

On this basis, in the step S100, the process of acquiring the node association map may specifically include:

and A1, acquiring the at least two nodes.

Specifically, it has been described in the foregoing that the node association graph includes at least two nodes, then this step may acquire at least two nodes, and optionally, the at least two nodes may have different priorities.

A2, determining the node types of each pair of two nodes with the association relationship.

Optionally, the nodes in the node association graph may include different node types, and the node types to which the two nodes having the association relationship in each pair belong may be different, so in this step, the node types to which the two nodes having the association relationship in each pair belong may be determined.

A3, determining the priority levels corresponding to the two nodes respectively based on the priority levels corresponding to the preset node types respectively.

Specifically, each node type corresponds to a different priority level, the step may preset a priority level corresponding to each node type, and further may determine, based on the priority level, a priority level corresponding to each pair of two nodes having an association relationship.

And A4, determining the direction of the directed edge connecting the two nodes based on the priority levels corresponding to the two nodes respectively, so as to obtain the directed edges corresponding to the two nodes with incidence relation respectively.

In particular, it has been explained in the foregoing that the edges included in the node association graph may be directed edges, and the direction of one directed edge is that a node with a high priority points to a node with a low priority. Based on this, after determining the priority level corresponding to each pair of two nodes having an association relationship, the direction of the directed edge connecting the two nodes may be determined based on the priority level, and then the directed edge corresponding to the two nodes is obtained. Since the node association graph may include a plurality of pairs of two nodes having an association relationship, a plurality of directed edges corresponding to the plurality of pairs of two nodes having an association relationship may be obtained in this step.

Referring to FIG. 5, a schematic diagram of a node dependency graph including directed edges is illustrated. The nodes in the node association graph in fig. 5 include 5 types of nodes, which are respectively an enterprise service ID type, a mobile phone number type, a mailbox type, an S/N type, and a Cookie type, sorted from high to low according to priority, and for differentiation, the nodes of different node types are respectively represented by triangles, hexagons, quadrilaterals, circles, and pentagons, as shown in fig. 5, the nodes belonging to the enterprise service ID type are represented by triangles; representing nodes belonging to the mobile phone number type by hexagons; representing nodes belonging to the mailbox type by quadrangles; nodes belonging to the S/N type are represented by circles and nodes belonging to the Cookie type are represented by pentagons. Then, for each pair of two nodes having an association relationship, it may be determined that the directions of the directed edges connecting the two nodes are from left to right, and then a node association graph including directed edges as shown in fig. 5 may be obtained.

In an embodiment of the application, a process of obtaining the first parameter in the step S110 is described, where the process may specifically include:

in an alternative manner, the first parameter may be determined according to the total number of nodes included in the association graph to be processed, that is:

if the total number of the nodes contained in the correlation diagram to be processed is greater than or equal to a first preset value, acquiring a first parameter representing that the correlation diagram to be processed contains the nodes respectively corresponding to different users; and if the number of the nodes contained in the association graph to be processed is less than the first preset value, acquiring a first parameter representing that the association graph to be processed does not contain the nodes respectively corresponding to different users.

Specifically, a first preset value may be preset, and when the total number of nodes included in the association graph to be processed is greater than or equal to the first preset value, the association graph to be processed includes nodes corresponding to two or more users respectively, and the obtained first parameter indicates that the association graph to be processed includes nodes corresponding to different users respectively; when the total number of the nodes contained in the correlation diagram to be processed is smaller than a first preset value, the correlation diagram to be processed only comprises the nodes respectively corresponding to one user, and the obtained first parameter indicates that the correlation diagram to be processed does not contain the nodes respectively corresponding to different users.

In another alternative, when the to-be-processed dependency graph includes at least one type of node, the application may determine the first parameter according to the number of nodes belonging to any type included in the to-be-processed dependency graph, that is:

if the number of the nodes belonging to any type and contained in the correlation diagram to be processed is larger than or equal to a corresponding second preset value, acquiring a first parameter representing that the correlation diagram to be processed contains nodes respectively corresponding to different users; and if the number of the nodes belonging to each type contained in the correlation diagram to be processed is respectively smaller than the corresponding second preset value, acquiring a first parameter representing that the correlation diagram to be processed does not contain the nodes respectively corresponding to different users.

Specifically, a second preset value may be set for each node type, when the number of nodes belonging to any type included in the association graph to be processed is greater than or equal to the corresponding second preset value, the association graph to be processed includes nodes corresponding to two or more users respectively, and the obtained first parameter indicates that the association graph to be processed includes nodes corresponding to different users respectively; when the number of the nodes belonging to each type contained in the correlation diagram to be processed is respectively smaller than the corresponding second preset value, the correlation diagram to be processed is shown to only contain the nodes respectively corresponding to one user, and the obtained first parameter shows that the correlation diagram to be processed does not contain the nodes respectively corresponding to different users.

In another alternative, when the to-be-processed dependency graph includes at least one type of node, the application may determine the first parameter according to the total number of nodes included in the to-be-processed dependency graph and the number of nodes belonging to any type included in the to-be-processed dependency graph, that is:

Specifically, a first preset value may be set for the total number of nodes included in the association graph to be processed, and a second preset value may be set for each node type, so that when the total number of nodes included in the association graph to be processed is greater than or equal to the first preset value, and the number of nodes belonging to any type included in the association graph to be processed is greater than or equal to the corresponding second preset value, it indicates that the association graph to be processed includes nodes respectively corresponding to two or more users, and at this time, the obtained first parameter indicates that the association graph to be processed includes nodes respectively corresponding to different users; when the total number of nodes contained in the association graph to be processed is smaller than a first preset value, and the number of nodes belonging to each type contained in the association graph to be processed is smaller than a corresponding second preset value, the association graph to be processed only includes nodes respectively corresponding to one user, and the acquired first parameter indicates that the association graph to be processed does not contain nodes respectively corresponding to different users.

In another embodiment of the application, when an edge included in the to-be-processed dependency graph is a directed edge, and a direction of one directed edge is that a node with a high priority level points to a node with a low priority level, in step S120, a process of acquiring a key node from nodes included in the to-be-processed dependency graph may specifically include:

and B1, acquiring at least one candidate edge node from the nodes contained in the correlation graph to be processed, wherein the degree of entry of the candidate edge node is 0 and the degree of exit is greater than 1 or the degree of exit is 0 and the degree of entry is greater than 1.

Specifically, when an edge included in the correlation graph to be processed is a directed edge, a candidate edge node may be determined according to the in-degree and the out-degree of each node in the correlation graph to be processed, where the candidate edge node is a node in which the in-degree is 0 and the out-degree is greater than 1 or the out-degree is 0 and the in-degree is greater than 1 in the correlation graph to be processed. Here, the in-degree is 0, which means that the number of directed edges using the candidate edge node as a pointing terminal is 0, and the out-degree is greater than 1, which means that at least 2 directed edges use the candidate edge node as a pointing start point. It will be appreciated that the number of candidate edge nodes included in the correlation graph to be processed is at least one.

Referring to fig. 6, a schematic diagram of determining candidate edge nodes in a dependency graph to be processed is illustrated. In the graph, the black bold nodes are all nodes with an in-degree of 0 and an out-degree of greater than 1 or with an out-degree of 0 and an in-degree of greater than 1, that is, candidate edge nodes in the correlation graph to be processed.

B2, obtaining the key node from the at least one candidate edge node.

Specifically, the key nodes are all nodes with an in-degree of 0 and an out-degree greater than 1 or with an out-degree of 0 and an in-degree greater than 1, that is, the key nodes are one or more of the candidate edge nodes, so the step may determine the key nodes from the candidate edge nodes determined in the previous step.

Considering that each pair of two nodes with association relation are obtained in the process of executing different events, and the number of executing different events may be different for each pair of two nodes with association relation, and the number is defined as a weight, the weights of the directed edges connecting each pair of two nodes with association relation may be the same and may be different. Therefore, on the basis of the previous embodiment, in this embodiment, the key node may also be determined from the candidate edge nodes according to the weight corresponding to each directed edge in the dependency graph to be processed. Based on this, the above B2, the process of obtaining the key node from the at least one candidate edge node may specifically include:

and B21, aiming at each candidate edge node, acquiring the maximum weight from the weights respectively corresponding to the directed edges connecting the candidate edge node so as to obtain the maximum weight respectively corresponding to the at least one candidate edge node.

Specifically, the directed edge connecting each candidate edge node corresponds to two or more weights, respectively, so that the step may determine, for each candidate edge node, the largest one of the two or more weights as the largest weight corresponding to each candidate edge node. Optionally, the number of candidate edge nodes included in the correlation map to be processed is the same as the number of maximum weights determined in this step. Optionally, the weights of different directed edges may be the same, and at this time, the number of candidate edge nodes included in the correlation diagram to be processed is smaller than the number of maximum weights determined in this step.

B22, obtaining the candidate edge node corresponding to the minimum weight from the maximum weights respectively corresponding to the at least one candidate edge node, where the candidate edge node corresponding to the minimum weight is the key node.

Specifically, after the maximum weight obtained in B21 is obtained, the minimum weight may be selected in this step, and the candidate edge node corresponding to the minimum weight is the key node. Optionally, the selected minimum weight may include a plurality of weights, and the plurality of minimum weights may correspond to obtain a plurality of key nodes.

Referring to fig. 7a-7b, schematic diagrams illustrating a process of determining a key node of candidate edge nodes are shown, wherein the determined candidate edge nodes are A, B, C, D, E, F, G respectively. In fig. 7a, for the candidate edge node a, the weights corresponding to the directed edges connecting to a are respectively 16 and 17, and the maximum weight 17 is selected as the maximum weight corresponding to the candidate edge node a; similarly, the maximum weight 18 may be selected as the maximum weight corresponding to the candidate edge node B; selecting the maximum weight 13 as the maximum weight corresponding to the candidate edge node C; selecting the maximum weight 11 as the maximum weight corresponding to the candidate edge node D; selecting the maximum weight 7 as the maximum weight corresponding to the candidate edge node E; selecting the maximum weight 5 as the maximum weight corresponding to the candidate edge node F; and selecting the maximum weight 2 as the maximum weight corresponding to the candidate edge node G.

Then, referring to fig. 7b, the minimum weight 2 is selected from the

maximum weights

17, 18, 13, 11, 7, 5, and 2, and the candidate edge node G corresponding to the minimum weight 2 is the key node.

In another embodiment of the present application, a process of at least disconnecting the edges between the key nodes and the at least one second node to obtain at least one target sub-association graph in the step S130 is described.

Specifically, in the step S130, the process of at least disconnecting the edges between the key nodes and the at least one second node to obtain the at least one target sub-association graph may specifically include:

and C1, disconnecting the edges between the key nodes and the at least one second node respectively to obtain at least one sub-association graph.

Specifically, it has been described in the foregoing that the probability that the key node and the second node belong to different users is the largest, so that in this step, edges between the key node and at least one second node can be broken, so that nodes belonging to different users can be separated, and thus at least one sub-association graph is obtained. Here, the number of different users corresponding to one sub-correlation diagram is smaller than the number of different users corresponding to the correlation diagram to be processed.

Referring to fig. 8a-8b, schematic diagrams illustrating a process of breaking an edge between a switch key node and a second node are shown. In fig. 8a, if the key node is G and the node H connected to it is the second node, the connection between G and H is broken, so that two sub-association graphs shown in fig. 8b can be obtained.

And C2, regarding each sub-association graph as a to-be-processed association graph, and returning to the step of acquiring the first parameter until the first parameter indicates that the to-be-processed association graph only contains nodes respectively corresponding to the same user, so as to obtain at least one target sub-association graph.

Specifically, the to-be-processed association graph may include nodes corresponding to two or more users, and in order to obtain that each sub-association graph includes only a node corresponding to one user, each sub-association graph obtained in C1 may be used as the to-be-processed association graph, to re-acquire the first parameter and the key node of each to-be-processed association graph, and disconnect the key node from the second node, so as to finally obtain at least one target sub-association graph including only a node corresponding to one user.

Referring to FIG. 9, a schematic diagram illustrating the determination of a target sub-association graph is shown. The two sub-correlation diagrams in fig. 8b are respectively taken as the correlation diagrams to be processed, and steps S110 to S130 are executed again, so that the 4 target sub-correlation diagrams shown in fig. 9 can be obtained finally.

The method is described in detail in the embodiments disclosed in the present application, and the method of the present application can be implemented by various types of apparatuses, so that the present application also discloses a processing apparatus, and specific embodiments are described in detail below.

Referring to fig. 10, fig. 10 is a schematic structural diagram of a processing apparatus disclosed in the embodiment of the present application.

As shown in fig. 10, the apparatus may include:

the first obtaining module 11 is configured to obtain a node association graph, where the node association graph includes at least two nodes and an edge connecting every two nodes, where an edge represents that two nodes connected by the edge have an association relationship, the association relationship represents that two nodes connected by the edge can be obtained at least in a process of executing a same event, and the node association graph is used as a to-be-processed association graph;

a second obtaining module 12, configured to obtain a first parameter, where the first parameter indicates whether the association graph to be processed includes nodes corresponding to different users respectively;

a third obtaining module 13, configured to obtain a key node from nodes included in the to-be-processed association graph if the first parameter indicates that the to-be-processed association graph includes nodes corresponding to different users, respectively;

a fourth obtaining module 14, configured to at least disconnect edges between the key nodes and the at least one second node, respectively, to obtain at least one target sub-association graph; one target sub-association graph corresponds to one user.

Optionally, the edges included in the association graph to be processed are directed edges, and the direction of one directed edge is that a node with a high priority points to a node with a low priority;

the third obtaining module may include:

Optionally, the to-be-processed association graph further includes a weight corresponding to each directed edge, where the weight corresponding to one directed edge represents the number of different events of two nodes connected to the directed edge obtained in the process of executing different events;

the second acquiring unit may include:

a maximum weight obtaining unit, configured to obtain, for each candidate edge node, a maximum weight from weights respectively corresponding to directed edges connecting the candidate edge node, so as to obtain maximum weights respectively corresponding to the at least one candidate edge node;

a key node determining unit, configured to obtain a candidate edge node corresponding to a minimum weight from maximum weights respectively corresponding to the at least one candidate edge node, where the candidate edge node corresponding to the minimum weight is the key node;

Optionally, the fourth obtaining module may include:

the third obtaining unit is configured to disconnect edges between the key nodes and the at least one second node, respectively, to obtain at least one sub-association graph;

and the fourth obtaining unit is used for taking each sub-association graph as a to-be-processed association graph, and returning to the step of obtaining the first parameter until the first parameter represents that the to-be-processed association graph only contains nodes respectively corresponding to the same user, so as to obtain at least one target sub-association graph.

Optionally, the first obtaining module may include:

a fifth obtaining unit, configured to obtain the at least two nodes;

a sixth obtaining unit, configured to determine, for each pair of two nodes having an association relationship, node types to which the two nodes belong respectively;

a seventh obtaining unit, configured to determine, based on priority levels respectively corresponding to preset node types, priority levels respectively corresponding to the two nodes;

and the eighth obtaining unit is configured to determine, based on the priority levels respectively corresponding to the two nodes, a direction of a directed edge connecting the two nodes, so as to obtain directed edges respectively corresponding to each pair of two nodes having an association relationship.

Optionally, the second obtaining module may include three optional implementations, and the specific implementation process may include:

the first method comprises the following steps:

a ninth obtaining unit, configured to obtain, if the total number of nodes included in the to-be-processed association graph is greater than or equal to a first preset value, first parameters that represent that the to-be-processed association graph includes nodes corresponding to different users, respectively; and if the number of the nodes contained in the association graph to be processed is less than the first preset value, acquiring a first parameter representing that the association graph to be processed does not contain the nodes respectively corresponding to different users.

And the second method comprises the following steps:

a tenth obtaining unit, configured to, if the number of nodes belonging to any type included in the to-be-processed association graph is greater than or equal to a corresponding second preset value, obtain a first parameter that represents that the to-be-processed association graph includes nodes corresponding to different users respectively; and if the number of the nodes belonging to each type contained in the correlation diagram to be processed is respectively smaller than the corresponding second preset value, acquiring a first parameter representing that the correlation diagram to be processed does not contain the nodes respectively corresponding to different users.

And the third is that:

an eleventh obtaining unit, configured to obtain a first parameter indicating that the to-be-processed dependency graph includes nodes corresponding to different users respectively, if the total number of nodes included in the to-be-processed dependency graph is greater than or equal to a first preset value and the number of nodes included in the to-be-processed dependency graph and belonging to any type is greater than or equal to a corresponding second preset value; and if the number of the nodes contained in the association graph to be processed is less than the first preset value, and the number of the nodes belonging to each type contained in the association graph to be processed is less than the corresponding second preset value, acquiring a first parameter representing that the association graph to be processed does not contain the nodes respectively corresponding to different users.

The processing device provided by the embodiment of the application can be applied to processing equipment, such as a mobile terminal, a PC terminal, a cloud platform, a server cluster and the like. Alternatively, fig. 11 shows a block diagram of a hardware structure of the processing device, and referring to fig. 11, the hardware structure of the processing device may include: at least one processor 1, at least one communication interface 2, at least one memory 3 and at least one communication bus 4;

in the embodiment of the application, the number of the processor 1, the communication interface 2, the memory 3 and the communication bus 4 is at least one, and the processor 1, the communication interface 2 and the memory 3 complete mutual communication through the communication bus 4;

the processor 1 may be a central processing unit CPU, or an application Specific Integrated circuit asic, or one or more Integrated circuits configured to implement embodiments of the present application, etc.;

the memory 3 may include a high-speed RAM memory, and may further include a non-volatile memory (non-volatile memory) or the like, such as at least one disk memory;

wherein the memory stores a program and the processor can call the program stored in the memory, the program for:

Alternatively, the detailed function and the extended function of the program may be as described above.

Embodiments of the present application further provide a readable storage medium, where a program suitable for being executed by a processor may be stored, where the program is configured to:

It should be noted that, in the present specification, the embodiments are all described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other. For the device or system type embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.

It is further noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method of processing, comprising:

acquiring a node association graph, wherein the node association graph comprises at least two nodes and an edge connecting two nodes with association relation in the at least two nodes, the association relation represents that the two nodes connected by the edge can be acquired at least in the process of executing the same event, the node association graph is taken as a to-be-processed association graph, the edge included in the to-be-processed association graph is a directed edge, and the direction of one directed edge is that a node with high priority points to a node with low priority;

at least disconnecting the edges between the key nodes and the at least one second node respectively to obtain at least one target sub-association graph; one target sub-association graph corresponds to one user;

wherein, obtaining the key node from the nodes contained in the correlation diagram to be processed comprises:

acquiring at least one candidate edge node from nodes contained in the association graph to be processed, wherein the degree of entry of the candidate edge node is 0 and the degree of exit is greater than 1 or the degree of exit is 0 and the degree of entry is greater than 1, the degree of entry being 0 means that the number of directed edges taking the candidate edge node as a pointing terminal is 0, and the degree of exit being greater than 1 means that at least 2 directed edges take the candidate edge node as a pointing starting point;

and acquiring the key node from the at least one candidate edge node.

2. The processing method according to claim 1, wherein said at least disconnecting the edges between the key nodes and the at least one second node, respectively, to obtain at least one target sub-association graph comprises:

3. The processing method according to claim 1, wherein the dependency graph to be processed further includes a weight corresponding to each directed edge, and the weight corresponding to one directed edge represents the number of different events that are obtained to two nodes connected to the directed edge during execution of the different events;

obtaining the key node from the at least one candidate node comprises:

4. The processing method according to claim 1, wherein the dependency graph to be processed includes at least one type of node, and the obtaining of the first parameter includes any one of:

or the like, or, alternatively,

5. The processing method according to claim 1, wherein the node association graph includes edges that are directed edges, and a direction of a directed edge is that a node with a high priority points to a node with a low priority; the obtaining of the node association graph comprises:

acquiring the at least two nodes;

6. A processing apparatus, comprising:

the first obtaining module is used for obtaining a node association graph, wherein the node association graph comprises at least two nodes and an edge connecting the two nodes with association relation in the at least two nodes, the association relation represents that the two nodes connected by the edge can be obtained at least in the process of executing the same event, the node association graph is taken as a to-be-processed association graph, the edge included in the to-be-processed association graph is a directed edge, and the direction of one directed edge is that a node with high priority level points to a node with low priority level;

the fourth obtaining module is configured to at least disconnect edges between the key nodes and the at least one second node, respectively, to obtain at least one target sub-association graph; one target sub-association graph corresponds to one user;

wherein the third obtaining module comprises:

a first obtaining unit, configured to obtain at least one candidate edge node from nodes included in the to-be-processed association graph, where an in-degree of the candidate edge node is 0 and an out-degree is greater than 1, or the out-degree is 0 and the in-degree is greater than 1, where the in-degree is 0 and indicates that the number of directed edges using the candidate edge node as a pointing terminal is 0, and the out-degree is greater than 1 and indicates that at least 2 directed edges use the candidate edge node as a pointing start point;

7. An electronic device, comprising:

a memory for storing a program;

and acquiring the key node from the at least one candidate edge node.

8. A readable storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps involved in the processing method of any one of claims 1 to 5.